OpenAI is good at unminifying code

https://glama.ai/blog/2024-08-29-reverse-engineering-minified-code-using-openai

by punkpeye • 2 years ago

931 304 2 years ago

glama.ai

nwoli• 2 years ago

Hopefully it can help do this on emscripten files too and help adblockers dechipher obfuscated code for that purpose

firtoz2• 2 years ago

Likewise for css class names

tgv• 2 years ago

I can imagine that finetuning a model for this task could be very successful. Time for another AI startup.

api2• 2 years ago

Anyone working on decompiler LLMs? Seems like we could render all code open source.

Training data would be easy to make in this case. Build tons of free GitHub code with various compilers and train on inverting compilation. This is a case where synthetic training data is appropriate and quite easy to generate.

You could train the decompiler to just invert compilation and the use existing larger code LLMs to do things like add comments.

croes• 2 years ago

Unminifying isn't decompiling.

It's just renaming variable and functions and inserting line breaks.

api2• 2 years ago

No but it’s a baby brother of the same problem. Compiling is a much more complex transform but ultimately it is just a code transform.

j_maffe5• 2 years ago

Minifying includes way more tricks than shorter variable names and removing white-space

BluSyn• 2 years ago

The potential implications of this are huge. Not just open sourcing, but imagine easily decompiling and modifying proprietary apps to fix bugs or add features. This could be a huge unlock, especially for long dead programs.

For legal reasons I bet this will become blocked behavior in major models.

roflmaostc• 2 years ago

I've never seen a law forbidding decompiling programs. But, some programs forbid to decompile applications by the license agreement. Further, you still don't have any right on this source code. It depends on the license...

johndough• 2 years ago

Anyone working on decompiler LLMs?

Here is an LLM for x86 to C decompilation: https://github.com/albertan017/LLM4Decompile

jraph3• 2 years ago

Seems like we could render all code open source

Unfortunately not really. Having the source is a first step, but you also need the rights to use it (read, modify, execute, redistribute the modifications), and only the authors of the code can grant these rights.

torginus• 2 years ago

Doesn't it count as 'clean room' reverse engineering - or alternatively, we could develop an LLM that's trained on the outputs and side-effects of any given function, and learns to reproduce the source code from that.

Or, going back to the original idea, while the source code produced in such a way might be illegal, it's very likely 'clean' enough to train an LLM on it to be able to help in reproducing such an application.

poikroequ3• 2 years ago

I think there's actually some potential here, considering LLMs are already very good at translating text between human languages. I don't think LLMs on their own would be very good, but a specially trained AI model perhaps, such as those trained for protein folding. I think what an LLM could do best is generate better decompiled code, giving better names to symbols, and generating code in a style a human is more likely to write.

I usually crap on things like chatgpt for being unreliable and hallucinating a lot. But in this particular case, decompilers already usually generate inaccurate code, and it takes a lot of work to fix the decompiled code to make it correct (I speak from experience). So introducing AI here may not be such a huge stretch. Just don't expect an AI/LLM to generate perfectly correct decompiled code and we're good (wishful thinking).

DonHopkins2• 2 years ago

Seems like we could render all code open source.

That's not how copyright and licensing works.

You could already break the law and open yourself up to lawsuits and prosecution by stealing intellectual property and violating its owners rights before there were LLMs. They just make it more convenient, not less illegal.

layer8• 2 years ago

It can’t really compensate for missing variable and function names, not to mention comments.

aengelke• 2 years ago

There was a paper about this at CGO earlier this year [1]. Correctness is a problem that is hard to solve, though; 50% accuracy might not be enough for serious use cases, especially given that the relation to the original input for manual intervention is hard to preserve.

[1] https://arxiv.org/abs/2305.12520

js82• 2 years ago

Seems like we could render all code open source.

I agree. I think "AI generating/understanding source code" is a huge red herring. If AI was any good at understanding code, it would just build (or fix) the binary.

And I believe how it will turn out to be, when we really have AI programmers, they will not bother with human-readable code, but code everything in machine code (and if they are tasked in maintaining existing system, they will understand in its entirety, across the SW and HW stack). It's kinda like diffusion models that generate images don't actually bother with learning drawing techniques.

Vampiero• 2 years ago

Why wouldn't AIs benefit from using abstractions? At the very least it saves tokens. Fewer tokens means less time spent solving a problem, which means more problem solving throughput. That is true for machines and people alike.

If anything I expect AI-written programs in the not so distant future to be incomprehensible because they're too short. Something like reading an APL program.

nnurmanov• 2 years ago

Yet another surprising side effects of LLMs.

8ndow• 2 years ago

Is it though? The developer tabs have an unminify button which yields similar results. JavaScript minification is not hard in any way and the guessing of variable names is not that hard given such a simple code example.

_joel• 2 years ago

If the training data's included both unminified and minified libs, then is it such a stretch?

interstice• 2 years ago

Have used Claude to reverse engineer some minified shopify javascript code recently. Definitely handy for unpicking things.

j_maffe5• 2 years ago

LLMs are excellent at text transformation. It's their core strength and I don't see it being used enough.

PaulHoule• 2 years ago

Particularly those that are basically linear, that don’t involve major changes in the order of things or a deep consideration of relationships between things.

They can’t sort a list but they can translate languages, for instance, given that a list sorted almost right is wrong but that we will often settle for an almost right translation.

msp26• 2 years ago

Isn't this already their main use case for business? We use them primarily for extracting structured data from other forms.

xanderlewis7• 2 years ago

It’s not only their core strength — it’s what transformers were designed to do and, arguably, it’s all they can do. Any other supposed ability to reason or even retain knowledge (rather than simply regurgitate text without ‘understanding’ its intended meaning) is just a side effect of this superhuman ability.

stavros• 2 years ago

I see your point, but I think there's more to it. It's kind of like saying "all humans can do is perceive and produce sound, any other ability is just a side-effect". We might be focusing too much on their mechanism for "perception" and overlooking other capabilities they've developed.

baq• 2 years ago

it’s all they can do

this overlooks how they do it. we don't really know. it might be logical reasoning, it might be a very efficient content addressable human-knowledge-in-a-blob-of-numbers lookup table... it doesn't matter if they work, which they do, sometimes scarily well. dismissing their abilities because they 'don't reason' is missing the forest for the trees in that they'd be capable of reasoning if they were able to run sat solvers on their output mid generation.

sitkack4• 2 years ago

Hinton claims they do reason. I am going to go with Hinton on this.

worldsayshi3• 2 years ago

One potential benefit should be that with the right tooling around it it should be able to translate your code base to a different language and/or framework more or less at the push of a button. So if a team is wondering if it would be worth it to switch a big chunk of the code base from python to elixir they don't have to wonder anymore.

I tried translating a python script to javascript the other day and it was flawless. I would expect it to scale with a bit of hand-railing.

adamdiy• 2 years ago

see projects like https://github.com/joshpxyne/gpt-migrate

think there's also a YC company recently focusing on the nasty, big migrations with LLM help

scarface_74• 2 years ago

ChatGPT is trained well enough on all things AWS that it can do a decent job translating Python based SDK code to Node and other languages, translate between CloudFormation/Terraform/CDK (in various languages).

It does a well at writing simple to medium complexity automation scripts around AWS.

If it gets something wrong, I tell it to “verify your answer using the documentation available on the web”

greenthrow• 2 years ago

The problem is the use case is where you don't care about the risk of hallucinations or you can validate the output without already having the data in a useful format. Plus you need to lack the knowledge/skill to do it more quickly using awk/python/perl/whatever.

worldsayshi3• 2 years ago

That's why having good test suites and tools are more important than ever.

j_maffe5• 2 years ago

I think text transformation is a sufficiently predictable task that one could make a transformer that completely avoids hallucinations. Most LLMs have high temperatures which introduces randomness and therefore hallucinations into the result.

runiq• 2 years ago

Please let this one have knock-on effects on reverse engineering.

skirge2• 2 years ago

See Binary Ninja's Sidekick plugin

bravetraveler• 2 years ago

LLMs are good at modeling and transforming text, news at 11. AI proponent hypes AI. I could go on, but I shouldn't have been this sarcastic to start with

chx• 2 years ago

You should be. I am facepalming at the topic and every single comment in here. It's so full of holes, the Swiss dairy industry went out of business.

albert_e3• 2 years ago

Should the title say ChatGPT or gpt-4 (the model) instead of OpenAI (the company)?

johnisgood• 2 years ago

I think it should not say the name of the company, but either ChatGPT or GPT-x.

punkpeye5• 2 years ago

It would have been a better title, yes.

ubj• 2 years ago

I agree, this would make the title more accurate.

cbm-vic-20• 2 years ago

I left my Kleenex next to the Xerox.

taneq2• 2 years ago

Better Hoover it up!

dantondwa• 2 years ago

There is a certain justice in the use of OpenAI as a name for their product, given that OpenAI has turned the generic technical GPT name into a brand.

ChadNauseam2• 2 years ago

The generative pretrained transformer was invented by OpenAI, and it seems reasonable for a company to use the name it gave to its invention in its branding.

Of course, they didn't invent Generative pretraining (GP) or transfomers (T) but AFAIK they were the first to publicly combine them

j_maffe5• 2 years ago

GPT is not a brand. A court ruling turned down that notion. It's a technology.

AlwaysRock• 2 years ago

And that they launch new models so often that GPT could mean 3.5, 4, 4o mini, or 4, just to name the ones I know off the top of my head.

whimsicalism• 2 years ago

more likely to get downvotes that way, potentially even downweighted

smusamashah• 2 years ago

LLMS are trained to predict next text. But examples like these look like they have also 'learned patterns'. If rot13 is applied on this minified code, will LLM still find meaning in it? if it still could, its more than just next tokens. Need to try it.

edit: chatgpt found out that its rot13 and couldn't explain the code directly without deobfuscating it first.

Tiberium• 2 years ago

Claude 3.5 Sonnet can natively speak double base64 encoded English. And I do mean it - you can double b64 encode something, send to it, and it'll respond as if it was normal English. Obviously base64 is a simpler transformation than rot13, but no GPT models can deal with double b64.

mistercow5• 2 years ago

Obviously base64 is a simpler transformation than rot13

Is it? It’s probably more obscuring from an LLM’s perspective, assuming the LLM has seen enough rot13 text during training. Spaces and punctuation are untouched by rot13, unlike base64, which means that word and sentence boundaries will still be denoted by tokens that denote those boundaries in plaintext.

knome• 2 years ago

it appears that openai's gpt-4 model can speak base64 as well. I jumped to your comment seeing if anyone else had tried it following the OP. double b64 I didn't try, but that is interesting.

$ ask4 ' what does dGhhdCBpcyBxdWl0ZSBpbnRlcmVzdGluZw== decode to? ' A "dGhhdCBpcyBxdWl0ZSBpbnRlcmVzdGluZw==" is a Base64 encoded string. When decoded, It translates to "that is quite interesting" in English.

GaggiX4• 2 years ago

I asked Claude 3.5 Sonnet a question in Italian in rot13 and it replied in Italian in rot13, there are a few typos but it's perfectly understandable.

mewpmewp2• 2 years ago

I tried with GPT-4o and it also responded in rot13, the response was on topic, but quite non-sensical, like GPT-2 or lower level.

However I can confirm that Claude was able to identify that it's rot13 and also respond properly.

ervinxie• 2 years ago

LLMs are very good at text reading. LLMs read tokenized text, while human use eyes to view words. Another scenario is that ChatGPT is good at analyzing cpp template error messages, which are usually long and hard to understand for human.

lifthrasiir19• 2 years ago

JS minification is fairly mechanical and comparably simple, so the inversion should be relatively easy. It would be of course tedious enough to be manually done in general, but transformations themselves are fairly limited so it is possible to read them only with some notes to track mangled identifiers.

A more general unminification or unobfuscation still seems to be an open problem. I wrote handful of programs that are intentionally obfuscated in the past and ChatGPT couldn't understand them even at the surface level in my experience. For example, a gist for my 160-byte-long Brainfuck interpreter in C had some comment trying to use GPT-4 to explain the code [1], but the "clarified version" bore zero similarity with the original code...

[1] https://gist.github.com/lifthrasiir/596667#gistcomment-47512...

panda-giddiness• 2 years ago

JS minification is fairly mechanical and comparably simple, so the inversion should be relatively easy.

Just because a task is simple doesn't mean its inverse need be. Examples:

  - multiplication / prime factorization
  - deriving / integrating
  - remembering the past / predicting the future

Code unobfuscation is clearly one of those difficult inverse problems, as it can be easily exacerbated by any of the following problems:

  - bugs
  - unused or irrelevant routines
  - incorrect implementations that incidentally give the right results

In that sense, it would be fortunate if chatGPT could give decent results at unobfuscating code, as there is no a priori expectation that it should be able to do so. It's good that you've also checked chatGPT's code unobfuscation capabilities on a more difficult problem, but I think you've only discovered an upper limit. I wouldn't consider the example in the OP to be trivial.

lifthrasiir19• 2 years ago

Of course, it is not generalizable! In my experience though, most minifiers do only the following:

- Whitespace removal, which is trivially invertible.

- Comment removal, which we never expect to recover via unminification.

- Renaming to shorter names, which is tedious to track but still mechanical. And most minifiers have little understanding of underlying types anyway, so they are usually very conservative and rarely reuse the same mangled identifier for multiple uses. (Google Closure Compiler is a significant counterexample here, but it is also known to be much slower.)

- Constant folding and inlining, which is annoying but can be still tracked. Again, most minifiers are limited in their reasoning to do extensive constant folding and inlining.

- Language-specific transformations, like turning `a; b; c;` into `a, b, c;` and `if (a) b;` into `a && b;` whenever possible. They will be hard to understand if you don't know in advance, but there aren't too many of them anyway.

As a result, minified code still remains comparably human-readable with some note taking and perseverance. And since these transformations are mostly local, I would expect LLMs can pick them up by their own as well.

(But why? Because I do inspect such programs fairly regularly, for example for comments like https://news.ycombinator.com/item?id=39066262)

drakythe• 2 years ago

As a point of order Code Minification != Code Obfuscation.

Minification does tend to obfuscate as as side effect, but it is not the goal, so reversing minification becomes much easier. Obfuscation on the other hand can minify code, but crucially that isn't the place it starts from. As the goal is different between minificaiton and obfuscation reversing them takes different efforts and I'd much rather attempt to reverse minification than I would obfuscation.

I'd also readily believe there are hundreds/thousands of examples online of reverse code minification (or here is code X, here is code X _after_ minifcation) that LLMs have ingested in their training data.

GaggiX4• 2 years ago

Random try (the first one) with Claude 3.5 Sonnet: https://claude.site/artifacts/246c1b1a-3088-447a-a526-b1e716...

I'm not on PC so it's not tested.

lifthrasiir19• 2 years ago

That's much better in that most of the original code remains present and comments are not that far off, but its understanding of global variables are utterly wrong (to be expected though, as many of them serve multiple purposes).

Max-q• 2 years ago

Converting a picture from color to black and white is a fairly simple task. Getting back the original in color is not easy. This is if course due to data lost in the process.

Minification works in the same way. A lot of information needed for understanding the code is lost. Getting back that information can be a very demanding task.

lifthrasiir19• 2 years ago

But it is not much different from reading through badly documented codes without any comments or meaningful names. In fact, many codes to be minified are not that bad and thus it is often possible to infer the original code just from its structure. It is still not a trivial task, but I think my comment never implied that.

Earw0rm• 2 years ago

Yep, I've tried to use LLMs to disassemble and decompile binaries (giving them the hex bytes as plaintext), they do OK on trivial/artificial cases but quickly fail after that.

johnfn2• 2 years ago

JS minification is fairly mechanical and comparably simple, so the inversion should be relatively easy.

This is stated as if it's a truism, but I can't understand how you can actually believe this. Converting `let userSignedInTimestamp = new Date()` to `let x = new Date()` is trivial, but going the other way probably requires reading and understanding the rest of the surrounding code to see in what contexts `x` is being used. Also, the rest of the code is also minified, making this even more challenging. Even if you do all that right, it's at best it's still a lossy conversion, since the name of the variable could capture characteristics that aren't explicitly outlined in the code at all.

viscanti2• 2 years ago

Because of how trivial that step is, it's likely pretty easy to just take lots of code and minify it. Then you have the training data you need to learn to generate full code from minified code. If your goal is to generate additional useful training data for your LLM, it could make sense to actually do that.

hluska• 2 years ago

And I can’t understand why any reasonably intelligent human feels the need to be this abrasive. You could educate but instead you had to be condescending.

lifthrasiir19• 2 years ago

You are technically true, but I think you should try some reverse engineering to see that it is usually possible to reconstruct much of them in spite of the amount of transformations made. I do understand that this fact might be hard to believe without any prior.

EDIT: I think I got why some comments complain I downplayed the power of LLM here. I never meant to, and I wanted to say that the unminification is a relatively easy task compared to other reverse engineering tasks. It is great we can automate the easy task, but we still have to wait for a better model to do much more.

015a• 2 years ago

The act of reducing the length of variable names by replacing something descriptive (like "timeFactor") with something much shorter ("i") may be mechanical and simple, but it is destructive and reversing that is not relatively easy; in fact, its impossible to do without a fairly sophisticated understanding of what the code does. That's what the LLM did for this; which isn't exactly surprising, but it is cool; being so immediately dismissive isn't cool.

lifthrasiir19• 2 years ago

I never meant to be dismissive, in fact my current job is to build a runtime for ML accelerator! I rather wanted to show that unminification is much easier than unobfuscation, and that the SOTA model is yet to do the latter.

Also, it should be noted that the name reconstruction is not a new problem and was already partly solved multiple times before the LLM era. LLM is great in that it can do this without massive retraining, but the reconstruction depends much on the local context (which was how earlier solutions approached the problem), so it doesn't really show its reasoning capability.

spacecadet2• 2 years ago

I use LLMs to assist with reverse engineering all the time right now. From minified, to binary, alongside Ghidra, its very helpful.

GaggiX4• 2 years ago

Can you provide more details? I'm curious about the performance and limitations of these models.

spacecadet2• 2 years ago

Like all LLMs you greatly benefit from prior experience or you risk just falling for hallucinations which is a limitation of a non-deterministic black box, and degrades performance relative to the task. Ive commented in other threads, LLMs are great at amplifying my output in an area I already have domain knowledge in. I think this is why people fail to realize any gains or give up, they think it will unlock areas they dont fully understand themselves. Blind leading the blind problem.

Tepix• 2 years ago

punkpeye could also have asked the LLM to replace the cryptic function and variable names with nice ones. I'm hopeful it would have done a good job.

fergie• 2 years ago

* takes out soap box and stands on it *

We should go back to uncompiled JavaScript code, our democracy depends on it.

lifthrasiir19• 2 years ago

Or learn to read minified JS code, which is actually not that difficult! (But you do have to take notes to track identifiers.)

creesch• 2 years ago

This is very close to how I often use LLMs [0]. A first step in deciphering code where I otherwise would need to, to use the authors words, power through reading the code myself.

It has been incredibly liberating to just feed it a spaghetti mess, ask to detangle it in a more readable way and go from there.

As the author also discovered, LLMs will sometimes miss some details, but that is alright as I will be catching those myself.

Another use case is when I understand what the code does, but can't quite wrap my head around why it is done in that specific way. Specifically, where the author of the code is no longer with the company. I will then simply put the method in the LLM chat, explain what it does, and just ask it why some things might be done in a specific way.

Again, it isn't always perfect, but more often than not it comes with explanations that actually make sense, hold up under scrutiny and give me new insights. It actually has prevented me once or twice from refactoring something in a way that would have caught me headaches down the line.

[0] chatGPT and more recently openwebUI as a front end to various other models (Claude variants mostly) to see the differences. Also allows for some fun concepts of having different models review each others answers.

xanderlewis7• 2 years ago

Is there any reason why it’s ‘OpenAI’ in the title rather than ‘ChatGPT’?

philipwhiuk• 2 years ago

It's the title of the blog post.

xanderlewis7• 2 years ago

Yeah... that's what I'm asking about

eqvinox• 2 years ago

Okay, but if the unminified code doesn't match the minified code (as noted at the end "it looks like LLM response overlooked a few implementation details"), that massively diminishes its usefulness — especially since in a lot of cases you can't trivially run the code and look for differences like the article does.

[ed.: looks like this was an encoding problem, cf. thread below. I'm still a little concerned about correctness though.]

punkpeye5• 2 years ago

This refers to the fact that ChatGPT generated version is missing some characters that are used in the original example. Namely, [looks like HN does not allow me to paste unicode characters, but I am referring to the block characters] can be seen in their version, but cannot be seen in the ChatGPT generated version. However, it very well might be that it is simply because I didn't include all the necessary context.

Discrediting the entire output because a few missing characters would be very pedantic.

Otherwise, the output is identical as far as I can tell by looking at it.

Joker_vD2• 2 years ago

It's because the author miscopy-pasted the original code: those "â–‘â–’â–“â–ˆ" at the end of the O5 string are supposed to be the block characters. E.g. "â–‘" in Windows-1252 [0] is 0xE2 0x96 0xE2 which, in UTF-8, exactly the encoding for U+2592 MEDIUM SHADE [1].

[0] https://en.wikipedia.org/wiki/Windows-1252#Character_set

[1] https://www.compart.com/en/unicode/U+2592

lifthrasiir19• 2 years ago

It does seem that the unminified code is very close to the original. In some cases ChatGPT even did its own refactoring in addition to the unminification:

    // ORIGINAL:
    j.useEffect(() => {
        function r() {
            n({ height: window.innerHeight, width: window.innerWidth });
        }
        if (typeof window < "u") return n({ height: window.innerHeight, width: window.innerWidth }), window.addEventListener("resize", r), () => window.removeEventListener("resize", r);
    }, []),

    // UNMINIFIED:
    useEffect(() => {
      const handleResize = () => {
        setSize({ height: window.innerHeight, width: window.innerWidth });
      };

      // Initial size setting
      handleResize();

      window.addEventListener('resize', handleResize);
      return () => {
        window.removeEventListener('resize', handleResize);
      };
    }, []);

Note that the original code doesn't call `handleResize` immediately, but have its contents inlined instead. (Probably the minifier did the actual inlining.) The only real difference here is a missing `if (typeof window < "u")` condition.

sabbaticaldev2• 2 years ago

the condition is a constant so it can be safely removed

Mashimo• 2 years ago

He also told it to reimplement from JavaScript to TypeScript.

I would guess if he just told it to rename the variables and method first, it would have been closer to the original.

jehna112• 2 years ago

You need to use another tool to do the actual renames, like HumanifyJS does:

https://github.com/jehna/humanify

tanepiper• 2 years ago

I find LLMs good at these kind of tasks, also converting between CSV to JSON for example (although you have to remind it not to be lazy and do the whole file)

amelius2• 2 years ago

This post basically says that I don't need to document my code anymore. No more comments, they can be generated automatically. Hurray!

skirge2• 2 years ago

what if the comment doesn't match what you intended to write?

elicash• 2 years ago

Maybe it's better for the comment to match the code you wrote, not the code you intended to write.

codr72• 2 years ago

Unfortunately the comments that could be generated are exactly the ones that should never be written. You want the comment to explain why, the information missing from the code.

maeln5• 2 years ago

This is something I always disagreed with. In my experience, I rather read a short comment explaining what is the purpose of a block of code, than trying to decipher it. Yes, code "should speak for itself", but reading a comment is almost always faster than reading blocks of code. And then there is also documentation (if you include it in what you define as comment). I much rather go through a website, with a search function, example, description, made with some docgen tool, than having to go through a library or programming language source code every time I need to remember how to do X, or if object B has implement function Y ...

sherburt3• 2 years ago

// This is an integer containing the accountId

int accountId;

We truly live in the future

VMG• 2 years ago

it is also pretty good at decompiling - try feeding it the output of https://godbolt.org/

netsec_burn• 2 years ago

I recently learned this too, just a few months ago. Ended up making a frontend so I could do it automatically: https://decompiler.zeroday.engineering/

samstave• 2 years ago

Dont know if this will apply directly here, but --

As someone who is "not a developer" - I use the following process to help my:

1. I setup StyleGuide rules for the AI, telling it how to write out my files/scripts:

- Always provide full path, description of function, invocation examples, and version number.

- Frequently have it summarize and explain the project, project logic, and a particular file's functions.

- Have it create a README.MD for the file/project

- Tell it to give me mermaid diagrams and swim diagrams for the logic/code/project/process

- Close prompts with "Review, Explain, Propose, Confirm, Execute" <-- This has it review the code/problem/prompt, explain what it understands, propose what its been asked to provide, confirm that its correct or I add mroe detail here - then execute and go with creating the artifacts.

I do this because Claude and ChatGPT are FN malevelant in their ignoring of project files/context - and their hallucinate as soon as their context window/memory fills up.

Further they very frequently "forget" to refer to the project context files uploaded/artifacts they themselves have proposed and written etc.

But - asking for a readme with code mermaid and logic is helpful to keep me on track.

viraptor• 2 years ago

Agents like Aider or Plandex wrap that up nicely. They do the automatic review and have a very verbose description of the edit format. If you do that often manually, it may be worth testing their prepackaged approach.

foxhop• 2 years ago

Here's a hint, STOP MINIFYING CODE! gzip over transport is enough.

lifthrasiir19• 2 years ago

Not exactly, because you still have to pay any distinct identifier present in your code. Also many minifiers do constant folding and inlining and remove comments, any of which almost surely remove redundant or unused information to compress.

mistercow5• 2 years ago

I don’t think they’re saying that minifying provides no additional space savings, but rather that those additional savings are small and not worth the tradeoffs.

shubhamjain2• 2 years ago

An interesting use-case of this capability is refactoring, which, for me, ChatGPT has been unmistakably good at. It's amazing how I can throw garbage code I wrote at ChatGPT, ask it to refactor, and get clean code that I can use without worrying if it's going to work or not, because in 99% of cases it works without breaking anything.

Sharlin2• 2 years ago

What language(s), out of interest?

shubhamjain2• 2 years ago

I use node.js, but I think it will work for anything. I recommend trying small chunks first vs dumping your whole file.

rpigab• 2 years ago

I can see some ways to use this and easily check that the LLM is not hallucinating parts of it, because you can ask the LLM to unminify (or deobfuscate) some component, then request unit tests to be written by the LLM, then humanly check that the unit tests are meaningful and that they don't miss things on the unminified code, then run the tests on the original minified version to confirm the LLM's work, maybe set up some mutation testing if it is relevant.

ziptron• 2 years ago

I apologize, GPT-4, for mistakenly accusing you of making mistakes.

I am testing large language models against a ground truth data set we created internally. Quite often when there is a mismatch, I realize the ground truth dataset is wrong, and I feel exactly like the author did.

SoftTalker• 2 years ago

Apologizing to a program seems rather silly though. Do you apologize to your compiler when you have a typo in your code, and have to make it do all that work again?

digging• 2 years ago

If the compiler could listen and update its functions based on the tone of what I said to it, yes I probably would.

jehna112• 2 years ago

Author of HumanifyJS here! I've created specifically a LLM based tool for this, which uses LLMs on AST level to guarantee that the code keeps working after the unminification step:

https://github.com/jehna/humanify

punkpeye5• 2 years ago

Looks useful! I will update the article to link to this tool. Thanks for sharing!

jehna112• 2 years ago

Super, thank you for adding the link! It really helps to get people to find the tool

firtoz2• 2 years ago

More tools should be built on ASTs, great work!

I'm still waiting for the AST level version control tbh

jansvoboda11• 2 years ago

Unison supposedly has an AST-aware version control system: https://www.unison-lang.org/

rightonbrother• 2 years ago

Smalltalk envy source controll

fny• 2 years ago

Is it possible to add a mode that doesn't depend on API access (e.g. copy and paste this prompt to get your answer)? Or do you make roundtrips?

jehna112• 2 years ago

There is a fully local mode that does not use ChatGPT at all – everything happens on your local machine.

API access of ChatGPT mode is needed as there are many round trips and it uses advanced API-only tricks to force the LLM output.

KolmogorovComp• 2 years ago

Thanks for your tool. Have you been able to quantify the gap between your local model and chatgpt in terms of ‘unminification performance’?

jehna112• 2 years ago

At the moment I haven't found good ways of measuring the quality between different models. Please share if you have any ideas!

For small scripts I've found the output to be very similar between small local models and GPT-4o (judging by a human eye).

cryptoz• 2 years ago

Finally someone else using ASTs while working with LLMs and modifying code! This is such an under-utilized area. I am also doing this with good results: https://codeplusequalsai.com/static/blog/prompting_llms_to_m...

jehna112• 2 years ago

Super interesting! Since you're generating code with LLMs, you should check out this paper:

https://arxiv.org/pdf/2405.15793

It uses smart feedback to fix the code when LLMs occasionally do hiccups with the code. You could also have a "supervisor LLM" that asserts that the resulting code matches the specification, and gives feedback if it doesn't.

sebstefan• 2 years ago

What kind of question does it ask the LLM? Giving it a whole function and asking "What should we rename <variable 1>?" repeatedly until everything has been renamed?

Asking it to do it on the whole thing, then parsing the output and checking that the AST still matches?

jehna112• 2 years ago

For each variable:

1. It asks the LLM to write a description of what the variable does

2. It asks for a good variable name based on the description from 1.

3. It uses a custom Babel plugin to do a scope-aware rename

This way the LLM only decides the name, but the actual renaming is done with traditional and reliable tools.

boltzmann-brain• 2 years ago

how do you make an LLM work on the AST level? do you just feed a normal LLM a text representation of the AST, or do you make an LLM where the basic data structure is an AST node rather than a character string (human-language word)?

dunham• 2 years ago

It looks like they're running `webcrack` to deobfuscate/unminify and then asking the LLM for better variable names.

WhitneyLand• 2 years ago

The frontier models can all work with both source code and ASTs as a result of their standard training.

Knowing this raises the question, which is better to feed an LLM source code of ASTs?

The answer is really it depends on the use case, there are tradeoffs. For example keeping comments intact possibly gives the model hints to reason better. On the other side, it can be argued that a pure AST has less noise for the model to be confused by.

There are other tradeoffs as well. For example, any analysis relating to coding styles would require the full source code.

jehna112• 2 years ago

I'm using both a custom Babel plugin and LLMs to achieve this.

Babel first parses the code to AST, and for each variable the tool:

1. Gets the variable name and surrounding scope as code

2. Asks the LLM to come up with a good name for the given variable name, by looking at the scope where the variable is

3. Uses Babel to make the context-aware rename to AST based on the LLM's response

thomassmith65• 2 years ago

Would it be difficult to add a 'rename from scratch' feature? I mean a feature that takes normal code (as opposed to minified code) and (1) scrubs all the user's meaningful names, (2) chooses names based on the algorithm and remaining names (ie: the built-in names).

Sometimes when I refactor, I do this manually with an LLM. It is useful in at least two ways: it can reveal better (more canonical) terminology for names (eg: 'antiparallel_line' instead of 'parallel_line_opposite_direction'), and it can also reveal names that could be generalized (eg: 'find_instance_in_list' instead of 'find_animal_instance_in_animals').

jehna112• 2 years ago

Yes, I think you could use HumanifyJS for that. The way it works is that:

1. I ask LLM to describe what the meaning of the variable in the surrounding code

2. Given just the description, I ask the LLM to come up with the best possible variable name

You can check the source code for the actual prompts:

https://github.com/jehna/humanify/blob/eeff3f8b4f76d40adb116...

thrdbndndn2• 2 years ago

Does it work with huge files? I'm talking about something like 50k lines.

Edit: I'm currently trying it with a mere 1.2k JS file (openai mode) it's only 70% done after 20 minutes. Even if it works therodically with 50k LOC file, I don't think you should try.

kingsloi• 2 years ago

It has this in the README

Large files may take some time to process and use a lot of tokens if you use ChatGPT. For a rough estimate, the tool takes about 2 tokens per character to process a file:
echo "$((2 * $(wc -c < yourscript.min.js)))" So for refrence: a minified bootstrap.min.js would take about $0.5 to un-minify using ChatGPT.
Using humanify local is of course free, but may take more time, be less accurate and not possible with your existing hardware.

jehna112• 2 years ago

It does work with any sized file, although it is quite slow if you're using the OpenAI API. HumanifyJS works so it processes each variable name separately, and keeps the context size manageable for an LLM.

I'm currently working on parallelizing the rename process, which should give orders of magnitude faster processing times for large files.

benreesman• 2 years ago

Came here to say Humanify is awesome both as a specific tool and in my opinion a really great way to think about how to get the most from inherently high-temperature activities like modern decoder nucleus sampling.

bgirard• 2 years ago

How well does it compare to the original un-minified code if you compare it against minify + humanify. Would be neat if it can improve mediocre code.

jehna112• 2 years ago

On structural level it's exactly 1-1: HumanifyJS only does renames, no refactoring. It may come up with better names for variables than the original code though.

anticensor• 2 years ago

Thanks for creating this megafier, can you add support for local LLMs?

jehna112• 2 years ago

Better yet, it already does have support for local LLMs! You can use them via `humanify local`

zamadatix• 2 years ago

It's a shame this loses one of the most useful aspects of LLM un-minifying - making sure it's actually how a person would write it. E.g. GPT-4o directly gives the exact same code (+contextual comments) with the exception of writing the for loop in the example in a natural way:

    for (var index = 0; index < inputLength; index += chunkSize) {

Comparing the ASTs is useful though. Perhaps there's a way to combine the approaches - have the LLM convert, compare the ASTs, have the LLM explain the practical differences (if any) in context of the actual implementation and give it a chance to make any changes "more correct". Still not guaranteed to be perfect but significantly more "natural" resulting code.

ouraf• 2 years ago

Depends on how many tokens you want to spend.

Making the code, fully commenting it and also giving an example after that might cost three times as much

strictnein• 2 years ago

As someone who has spent countless hours and days deobfuscating malicious Javascript by hand (manually and with some scripts I wrote), your tool is really, really impressive. Running it locally on a high end system with a RTX 4090 and it's great. Good work :)

nutanc• 2 years ago

Had tweeted about this sometime back. Found a component which was open source earlier and then removed and only minfied JS was provided. Give the JS to Claude and get the original component back. It even gave good class names to the component and function names.

Actually this opens up a bigger question. What if I like an open source project but don't like its license. I can just prompt AI by giving it the open source code and ask it to rewrite it or write in some other language. Have to look up the rules if this is allowed or will be considered copying and how will a judge prove?

lifthrasiir19• 2 years ago

Almost likely you would be found guilty because the intent matters. It is easy to check that the generated code is much similar to the original code, and you surely had a reason to bypass the original license. The exact legal reasoning would vary but any reasonable laywer would recommend you to do not.

In the historic Google v. Oracle suit, the only actual code that was claimed to be copied was a trivial `rangeCheck` function, but Google's intent and other circumstances like the identical code structure and documentation made it much more complicated, and the final decision completely bypassed the copyrightability of APIs possibly for this reason.

BeefWellington• 2 years ago

You can do this on minified code with beautifiers like js-beautify, for example. It's not clear why we need to make this an LLM task when we have existing simple scripts to do it?

mistercow5• 2 years ago

Beautifiers will restore whitespace, but they won’t rename variables by inferring their semantic meaning.

NohatCoder• 2 years ago

While this doesn't restore minified identifiers, like the LLM version claims to do, it tends to help a lot with understanding the code. Usually minified code still has the original identifiers in global function names, object attributes, DOM classes and a few other places where it is hard to guarantee no side effects of name mangling. This makes guessing the purpose of the remaining identifiers substantially easier to a human, and it is probably also the main reason why an LLM is capable of making reasonable guesses at what they could reasonably be called.

l5870uoo9y• 2 years ago

It is also shockingly good at converting/extracting data to CSV or JSON, but not JSONL. Even the less capable model, `gpt-4o-mini`, can "reliably" parse database schemas in various formats into CSV with the structure:

```csv table_name,column_name,data_type table_name,column_name1,data_type table_name,column_name2,data_type ... ```

I have been running it in production for months[1] as a way to import and optimize database schemas for AI consumption. This performs much better than including the `schema.sql` file in the prompt.

[1] https://www.sqlai.ai/app/datasources/add/database-schema/ai-...

Mc912• 2 years ago

It is good at unminifying and "minifying" as well.

I have been doing the Leetcode thing recently, and even became a subscriber to Leetcode.

What I have been doing is I go through the Grind 75 list (Blind 75 successor list), look for the best big O time and space editorial answer, which often has a Java example, and then go to ChatGPT (I subscribe) or Perplexity (don't subscribe to Pro - yet) and say "convert this to Kotlin", which is the language I know best. Jetbrains IDE or Android Studio is capable of doing this, but Perplexity and ChatGPT are usually capable of doing this as well.

Then I say "make this code more compact". Usually I give it some constraints too - keep the big O space and time complexity the same or lower it, keep the function signature of the assigned function the same, and keep the return explicit, make sure no Kotlin non-null assertions crop up. Sometimes I continually have it run these instructions on each version of the iterated code.

I usually test that the code compiles and returns the correct answers for examples after each iteration of compacting. I also copy answers from one to the other - Perplexity to ChatGPT and then back to Perplexity. The code does not always compile, or give the right answers for the examples. Sometimes I overcompact it - what is clear in four lines becomes too confusing in three compacted lines. I'm not looking for the most compact answer, but a clear answer that is as compact as possible.

One question asked about Strings and then later said, what if this was Unicode? So now for String manipulation questions I say assume the String is Unicode, and then at the end say show the answer for ASCII or Unicode. Sometimes the big O time is tricky - it is time O(m+n) say, but since m is always equal to or less than m in the program, it is actually O(n), and both Perplexity and ChatGPT can miss that until it is explained.

People bemoan Leetcode as a waste of time, but I am wasting even less time with it, as ChatGPT and Perplexity are helping give me the code I will be demonstrating in interviews. The common advice I have heard from everywhere is don't waste time trying to figure out the answers myself - just look at the given answers, learn them, and then look for patterns (like binary search problems, which are usually similar), so that is what I am doing.

Initially I was a ChatGPT and Perplexity skeptic for early versions of those sites, in terms of programming, as they stumbled more, but these self-contained examples and procedures they seem well-suited for. Not that they don't hallucinate or give programs that don't compile, or give the wrong answers sometimes, but it saves me time ultimately.

flerchin• 2 years ago

This does seem to be a smart use of the tools available to skip the grind and get to the point of the leetcode questions.

However, I wonder about this: What will you do in a live interview situation? Will you pull up ChatGPT?

Mc912• 2 years ago

I have been told by people working in $200k+/$300k+ SWE jobs to look up at the answers and just be able to regurgitate something along the lines of the Grind 75 answers as a first step.

As a next step - even within these 75 questions, Grind 75's eighth answer and fourteenth answer are answered essentially the same way, as are other questions in there. So the next step would be to see these patterns (binary search, priority queues, sliding window, backtracking) and how to answer them, and then be able to solve them in slightly novel problems (in the more complex questions I understand one might run into more than one of these patterns).

nprateem• 2 years ago

And shockingly shit at writing articles that don't sound like essays.

pogue• 2 years ago

Only thing I'd like to suggest is an option to search for Windows 11 compatible machines. With MS cutting off support for Windows 10 next year, making sure a machine has the system requirements needed.

However, I have seen a lot of sellers install W11 on non-compatible devices using a few tricks. I'm not sure how you check that in a search tool, but great job otherwise! I'll definitely be using this in the future (and I think you should pass everything through affiliate links! Pay for the upkeep at least)

jackconsidine• 2 years ago

That's interesting. It's gotten a lot better I guess. A little over a year ago, I tried to use GPT to assist me in deobfuscating malicious code (someone emailed me asking for help with their hacked WP site via custom plugin). I got much further just stepping through the code myself.

After reading through this article, I tried again [0]. It gave me something to understand, though it's obfuscated enough to essentially eval unreadable strings (via the Window object), so it's not enough on it's own.

Here was an excerpt of the report I sent to the person:

For what it’s worth, I dug through the heavily obfuscated JavaScript code and was able to decipher logic that it:
- Listens for a page load
- Invokes a facade of calculations which are in theory constant
- Redirects the page to a malicious site (unk or something)

[0] https://chatgpt.com/share/f51fbd50-8df0-49e9-86ef-fc972bca6b...

andrewmcwatters• 2 years ago

I’ve tried using LLMs to deobfuscate libraires like fingerprintjs-pro to understand what specific heuristics implementation details they use to detect bots.

They mostly fail. A human reverse engineer will still do better.

camillomiller2• 2 years ago

Most expensive unminify software in history

GaggiX4• 2 years ago

A human would be even more expensive.

camillomiller2• 2 years ago

Those pesky humans! To be fair, I think it’s not if you consider the sunken costs of LLMs.

Tistel• 2 years ago

This might be fun:

Train on java compiled to class files. Then go from class back to java.

Or even:

Train java compiled to class files, and have separate models that train from Clojure to class and Scala to class files. Then see if you can find some crufty (but important) old java project and go: crufty java -> class -> Clojure (or Scala).

If you could do the same with source -> machine instructions, maybe COBAL to C++! or whatever.

atemerev• 2 years ago

I think there are already decompilers and code analyzers at NSA like this. For 10 years or so.

igorguerrero• 2 years ago

This is something you don't need AI for, there are many decompilers out there already as well.

AI cannot even lint properly right now and you want it to decompile? good luck, there's too much hype going on people really think this is possible this year?

In the end always remember it's just autocomplete, it's pretty terrible at translations that are not natural language to natural language. I worked on a natural language to SQL and it was impossible to make it consistently generate valid SQL for Postgres, and I'm talking about natural language to SQL not virtual machine instructions...

sitkack4• 2 years ago

I agree, it is fun!

LLM source recovery from binaries is thing. The amazing part is that they are pretty good at adding back meaningful variable names to the generated source code.

gnutrino• 2 years ago

The site the post mentions for the original code (https://reactive.network/hackathon) is an accessibility nightmare.

lelandfe• 2 years ago

The garbled text is included in the tree as relevant, pronounceable, and constantly changing text. Here's Chrome's accessibility tree: https://imgur.com/a/V1589Jr

(I'd love if a screen reader user could upload some audio of how awful this sounds, by the by)

Please use `aria-hidden="true"` for stuff like this, it just removes the element from the accessibility tree. I've also emailed Reactive a link to this thread.

Here is a decent intro to ARIA things: https://www.smashingmagazine.com/2022/09/wai-aria-guide/

phatskat• 2 years ago

Big props for ARIA attributes - they’re so crucial for differently abled and impaired users. I’ve been combing through our project’s components lately to bring them up to design spec and have been taking a look at our accessibility - it’s so important and so easily missable for most engineers.

redbell• 2 years ago

That's an interesting finding so far!

The provided code is quite complex, but I'll break it down into a more understandable format, explaining its different parts and their functionalities.

Reading the above statement generated by ChatGPT, I asked myself: Will we live to the day where these LLMs could take a large binary executable as input, read it, analyze it, understand it, then reply with the above statement?

I followed up asking to "implement equivalent code in TypeScript and make it human readable" and got the following response.. To my surprise, the response is not only good enough, but it is also very readable.

What if this day came and we can ask these LLMs to rewrite the binary code in [almost] any programming language we want? This would be exciting, yet scary to just think about!

Teever• 2 years ago

https://sam.gov/opp/1e45d648886b4e9ca91890285af77eb7/view

martythemaniak• 2 years ago

You should give it a try and report back! One easy way would be to take an open-source Android app, compile the APK, then decompile it and feed the bytecode to an LLM and ask it to write the java/kotlin equivalent and compare the source and LLM decoded one.

fasteddie31003• 2 years ago

I recognized this a few months back when I wanted to see the algorithm that a website used to do a calculation. I just put the minified JS in ChatGPT and figured it out pretty easily. Let's take this a few steps out. What happens when a LLM can clone a whole SAAS app? Let's say I wanted to clone HubSpot. If an LLM can interact with a browser and figure out how a UI works and take code hints from un-mimified code I think we could see all SAAS apps be commoditized. The backend would be proprietary, but it could figure out API formats and suggest a backend architecture.

All this makes me think AI's are going to be a strong deflationary force in the future.

sgt101• 2 years ago

I was with you until:

If an LLM can interact with a browser and figure out how a UI works and take code hints from un-mimified code I think we could see all SAAS apps be commoditized. The backend would be proprietary, but it could figure out API formats and suggest a backend architecture.

whoooha! that's a lot of probing and testing of the SAAS that would be required in order to see how it behaved. SAAS aren't algorithms, they operate over data that's unseen on the front end as well...

All this makes me think AI's are going to be a strong deflationary force in the future.

I don't get this. I've literally never worked anywhere which had enough software engineers, we've been going on about software crisis for about 50 years and things are arguably worse than ever. The gap between the demand for good software (in the sense that allocating capital to producing it would be sensible) and the fulfillment of that demand is bigger than ever. We just don't have the mechanisms to make this work and to make it work at an economically viable level.

Then we get AI to help us and everyone thinks that the economy will shrink?

IncreasePosts• 2 years ago

You wouldn't necessarily need to do much probing - consider that the documentation would provide numerous hints to the agent as to what each endpoint was actually doing.

TheKarateKid• 2 years ago

Honestly, the value in most business software isn't the actual technology. It's the customer base and data held by the platforms.

Someone could already easily clone HubSpot relatively cheaply even if they hired developers, but that doesn't mean it will be anywhere near successful.

nashashmi• 2 years ago

Looks like the end is here for security via obscurity.

Julesman• 2 years ago

"Usually, I would just powerthrough reading the minimized code..."

Huh? Is this a thing? There are endless online code formatting sites. It takes two seconds. Why would anyone ever do this? I don't get it.

bredren• 2 years ago

Would have been cool if this had been used in that air con reverse engineering story yesterday.

I noticed while reading the blog entry that the author described using a search engine multiple times and thought, "I would have asked ChatGPT first for that."

MetaverseClub• 2 years ago

wow, is openAI such a great magic to you?

antonoo• 2 years ago

Is this code available in ChatGPT's training data?

Tried hard, couldn't find any similar code.

ninetyninenine4• 2 years ago

This is an example of superior intellectual performance to humans.

There’s no denying it. This task is intellectual. Does not involve rote memorization. There are not tons and tons of data pairs on the web of minimized code and unminified code for llms to learn from.

The llm understands what it is unminifying and it is in general superior to humans on this regard. But only in this specific subject.

indoordin0saur• 2 years ago

This is just transforming text.

There are not tons and tons of data pairs on the web of minimized code and unminified code for llms to learn from.

Are you sure about this? These can be easily generated from existing JS to use as a training set, not to mention the enormous amount of non-minified JS which is already used to train it.

ozr• 2 years ago

I'm bullish on AI, but I'm not convinced this is an example of what you're describing.

The challenge of understanding minified code for a human comes from opaque variable names, awkward loops, minimal whitespacing, etc. These aren't things that a computer has trouble with: it's why we minify in the first place. Attention, as a scheme, should do great with it.

I'd also say there is tons of minified/non-minified code out there. That's the goal of a map file. Given that OpenAI has specifically invested in web browsing and software development, I wouldn't be surprised if part of their training involved minified/unminified data.

ninetyninenine4• 2 years ago

minification and unminification is a heuristic process not an algorithmic one. It is akin to decompiling code or reverse engineering. It's a step beyond just your typical AI you see in a calculator.

etbebl• 2 years ago

These aren't things that a computer has trouble with

They are irrelevant for executing the code, but they're probably pretty relevant for an LLM that is ingesting the code and text and inferring its function based on other examples it has seen. It's definitely more impressive that an LLM can succeed at this without the context of (correct) variable names than with them.

danbolt• 2 years ago

I don’t claim expertise in AI or understanding intelligence, but could we also say that a pocket calculator really understands arithmetic and has superior intellectual performance compared to humans?

ninetyninenine4• 2 years ago

https://chatgpt.com/share/a430518b-16f8-47bb-8cb7-d9b8518376...

pornel• 2 years ago

Things are called AI only until they can be done well by a computer, and then they become just an algorithm.

There was a time when winning in Chess was a proof of humans' superior intellect, and then it became just an algorithm. Then Go.

mplewis• 2 years ago

Yeah, ok. Now count the number of Rs in this word.

plaidfuji• 2 years ago

I think I’d agree with your statement, in the same sense that a chess simulator or AlphaGo are superior to human intellect for their specific problem spaces.

LLMs are very good at a surprisingly broad array of semi-structured-text-to-semi-structured-text transformations, particularly within the manifold of text that is widely available on the internet.

It just so happens that lots of code is widely available on the internet, so LLMs tend to outperform on coding tasks. There’s also lots of marketing copy, general “encyclopedic” knowledge, news, human commentary, and entertainment artifacts (scripts, lyrics, etc). LLMs traverse those spaces handily as well. The capabilities of AI ultimately boil down to their underlying dataset and its quality.

gmd63• 2 years ago

Does not involve rote memorization. There are not tons and tons of data pairs on the web of minimized code and unminified code for llms to learn from.

GPT-4 has consumed more code than your entire lineage ever will and understands the inherent patterns between code and minified versions. Recognizing the abstract shape of code sans variable names and mapping in some human readable variable names from a similar pattern you've consumed from the vast internet doesn't seem farfetched.

okanat• 2 years ago

And a human can do it without seeing that amount of code and consuming less energy.

throwthrowuknow• 2 years ago

Umm yeah there are tons of examples in Github repos.

dontlikeyoueith2• 2 years ago

Yes, bow down before your god.

You people are so weird.

ninetyninenine4• 2 years ago

You're in denial. Nobody is worshipping a god here.

I'm simply saying the AI has superior performance to humans on this specific subject. That's all.

Why did you suddenly make this comment of "bowing before your god" when I didn't even mention anything remotely close to that?

I'll tell you why. Because this didn't come from me. It came from YOU. This is what YOU fear most. This is what YOU think about. And your fear of this is what blinds you to the truth.

hamstergene• 2 years ago

Why not count the fact that humans created a tool to help themselves at unminifying towards human score?

Having a computer multiplying 1000-digit numbers instantly is an example of humans succeeding at multiplying: by creating a tool for that first. Because what else is intellectually succeeding there? It’s not like the computer has created itself.

If one draws a boundary of human intelligence at the skull bone and does not count the tools that this very intelligence is creating and using as mere steps of problem solving process, then one will also have to accept that humans are not intelligent enough to fly into space or do surgery or even cook most of the meals.

seadan83• 2 years ago

This is an example of superior intellectual performance to humans.

So is too multiplying _many_ large numbers together.

The llm understands what it is unminifying and it is in general superior to humans on this regard.

Proof needed. I would grant in terms of speed as very likely to be true. In general, I do not know how accuracy would compare.

prologist11• 2 years ago

I have to ask the obvious question: how do you know the unminified code is semantically equivalent to the minified code? If someone knows how to verify LLM code transformations for semantic fidelity then I'd like to know because I think that would qualify as a major breakthrough for programming languages and semantics.

bdcravens• 2 years ago

I'm sure there's some number greater than zero of developers who are upset because they use minification as a means of obfuscation.

Reminds me of the tool that was provided in older versions of ColdFusion that would "encrypt" your code. It was a very weak algorithm, and didn't take long for someone to write a decrypter. Nevertheless some people didn't like this, because they were using this tool, thinking it was safe for selling their code without giving access to source. (In the late 90s/early 2000s before open source was the overwhelming default)

julianeon• 2 years ago

I bet there's some kind of use case/arms race soon to happen, like this:

Website offers some kind of contest which is partly dependent on obfuscated client side code.

Clever contestants can now through it into ChatGPT to improve their chances.

Now, it begins.

joshdavham• 2 years ago

Are there any serious security implications for this? Of course obfuscation through minification won't work anymore, but I'm not sure if that's really all that serious of an issue at the end of the day.

darepublic• 2 years ago

This is cool but I would have the worry that it got something wrong. Which is a general llm problem

emporas• 2 years ago

There is also topiary. From their website "The universal code formatter". I think it doesn't work with Javascript source for the moment, but it will surely work in the future.

[1] https://topiary.tweag.io/

lostdev• 2 years ago

Why not just use a beautifier?

gagabity• 2 years ago

Wonder how it does against other obfuscation and general decompiled code fixing.

cedws• 2 years ago

I’m hoping LLMs get better at decompiling/RE’ing assembly because it’s a very laborious process. Currently I don’t think they have enough in their training sets to be very good at it.

1vuio0pswjnm7• 2 years ago

Slightly off-topic but I remain perplexed at how "minified" Javascript is acceptable to software developers commenting online but terse code in any other language, e.g., one letter variable names, is unacceptable to a majority of software developer online commenters.

_rwo• 2 years ago

LLMs are great for self-contained boring tasks; recently I have started to refactor ruby tests with a simple prompt (getting rid of various rspec syntax in favor of more explicit notation at cost of code duplication - so kinda like unminifying things I guess) - works _ridiculously_ good as well

blueyes• 2 years ago

Unminification (obfuscation removal) can also be applied to text. Most specialties develop a jargon that allows insiders to communicate complex ideas quickly; that shorthand excludes outsiders. Large language models can make specialist jargon transparent and thereby expand the circle of people whose understanding applies to specialized fields. Essentially, they solve the problem of mapping specialized, jargonized concepts to things the outside reader already knows. Anyone who wants to learn needs this, and I hope it will become part of students' learning paths.

OpenAI is good at unminifying code

Related Stories